© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 10295
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions or desires

    oai_token-act-pair · gpt-3.5-turbo

    repeated expressions of desire or reluctance to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enhancement
    -0.72
    issance
    -0.71
    strength
    -0.71
    ements
    -0.68
     Excellent
    -0.67
     Compass
    -0.64
     Smooth
    -0.64
     Kinnikuman
    -0.63
     Apart
    -0.61
     Integrity
    -0.60
    POSITIVE LOGITS
     offend
    1.23
     jeopard
    1.13
     spoil
    1.13
     disturb
    1.10
     interfere
    1.09
     lose
    1.09
     waste
    1.08
     disappoint
    1.05
     incur
    1.05
     bother
    1.04
    Activations Density 0.067%

    No Known Activations